How much memory does GLM-4.7-Flash need at Q4?

The Q4 figure used here is 18.8 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.

What is the cheapest catalog device that runs GLM-4.7-Flash at Q4?

Radeon RX 7900 XT, list price $899.

How fast is GLM-4.7-Flash on the GeForce RTX 5060 Ti 16GB, as a bandwidth estimate?

About 255 tok/s at Q4. That is device bandwidth divided by active weight bytes, not a measured run.

No. GLM-4.7-Flash does not fit on the GeForce RTX 5060 Ti 16GB at Q4. The estimate is 18.8 GB and usable memory is 15.2 GB.

Can the GeForce RTX 5060 Ti 16GB run GLM-4.7-Flash?

Data updated 16 October 2026. Last reviewed the same day, when this catalog snapshot was written.

Usable memory on this 16 GB VRAM config is 15.2 GB (95% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for GLM-4.7-Flash on GeForce RTX 5060 Ti 16GB
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	18.8 GB	-3.6 GB	255 tok/s	No
Q8	32.3 GB	-17.1 GB	146 tok/s	No
FP16	74.9 GB	-59.7 GB	74.7 tok/s	No

GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.
Tokens/sec is a bandwidth roofline: GB/s divided by active weight GB. It is not a measured generation speed.

KV cache at 8K and 32K

FP16 KV-cache estimate: 0.4 GB at 8,192 tokens and 1.8 GB at 32,768 tokens. MLA models use the compressed latent plus the RoPE key from config.json, not a per-head KV.

Offload

About 3.1 GB of the Q4 weights sit outside usable VRAM. A partial offload would need at least that much free system RAM. This catalog does not record system RAM, so offload is not counted as a fit.

Ollama

This command pulls the Q4_K_M file from unsloth/GLM-4.7-Flash-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M

What fits instead

Cheapest catalog device at Q4: Radeon RX 7900 XT
Closest catalog model that still fits at Q4: gpt-oss-20b.

All hardware for GLM-4.7-Flash · All models for the GeForce RTX 5060 Ti 16GB

Questions

How much memory does GLM-4.7-Flash need at Q4?: The Q4 figure used here is 18.8 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Can the GeForce RTX 5060 Ti 16GB run GLM-4.7-Flash?: No. GLM-4.7-Flash does not fit on the GeForce RTX 5060 Ti 16GB at Q4. The estimate is 18.8 GB and usable memory is 15.2 GB.
What is the cheapest catalog device that runs GLM-4.7-Flash at Q4?: Radeon RX 7900 XT, list price $899.
How fast is GLM-4.7-Flash on the GeForce RTX 5060 Ti 16GB, as a bandwidth estimate?: About 255 tok/s at Q4. That is device bandwidth divided by active weight bytes, not a measured run.